chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[NPU] support GPTQ quantization on npu (#15203)

Browse Source 
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
This commit is contained in:
22dimensions
2026-01-29 15:48:18 +08:00
committed by GitHub
parent cbf90d70ff
commit 7b79326751
5 changed files with 259 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/layers/linear.py
+1
View File
@@ -61,6 +61,7 @@ WEIGHT_LOADER_V2_SUPPORTED = [
"TPUInt8LinearMethod",
"GPTQLinearMethod",
"FBGEMMFp8LinearMethod",
"GPTQLinearAscendMethod",
"ModelOptFp8LinearMethod",
"ModelOptFp4LinearMethod",
"IPEXAWQLinearMethod",